Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    Negations

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aset
    -0.07
     seulement
    -0.06
    =default
    -0.06
    (config
    -0.06
     pot
    -0.06
     也
    -0.06
    @m
    -0.06
     compliment
    -0.05
     cor
    -0.05
    首页
    -0.05
    POSITIVE LOGITS
     osoby
    0.07
    BUY
    0.07
    нє
    0.07
    -toggle
    0.07
     Mrs
    0.06
    них
    0.06
    ,cv
    0.06
     Nurs
    0.06
     výrob
    0.06
    rch
    0.06
    Act Density 0.049%

    No Known Activations